:orphan:

|rss_image|  **articles - 1/1** :ref:`Blog <ap-main-0>` :ref:`article (8) <ap-cat-article-0>` :ref:`articles (3) <ap-cat-articles-0>` :ref:`cours (6) <ap-cat-cours-0>` :ref:`module (7) <ap-cat-module-0>` :ref:`paper (3) <ap-cat-paper-0>`

.. |rss_image| image:: feed-icon-16x16.png
    :target: ../_downloads/rss.xml
    :alt: RSS

----


.. index:: articles


.. _ap-cat-articles-0:

articles - 1/1
++++++++++++++

.. blogpostagg::
    :title: Quelques articles intéressants
    :date: 2022-07-17
    :keywords: deep learning
    :categories: articles
    :rawfile: 2022/2022-07-17_library.rst

    Deep Learning
    
    * `Training Deep Networks without Learning Rates Through Coin Betting
      <https://arxiv.org/abs/1705.07795>`_
    * `Model Comparison and Calibration Assessment: User Guide for
      Consistent Scoring Functions in Machine Learning and Actuarial Practice
      <https://arxiv.org/abs/2202.12780>`_
    * `On Embeddings for Numerical Features in Tabular Deep Learning
      <https://arxiv.org/abs/2203.05556>`,
      `TABULAR DATA MODELING VIA CONTEXTUAL EMBEDDINGS
      <https://weasul.github.io/papers/7.pdf>`_
    * `MLGO: a Machine Learning Guided Compiler Optimizations Framework
      <https://arxiv.org/abs/2101.04808>`_
    * `Embedding Recycling for Language Models
      <https://arxiv.org/abs/2207.04993>`_
    * `Language Modelling with Pixels
      <https://arxiv.org/abs/2207.06991>`_
    * `XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale
      <https://paperswithcode.com/paper/xls-r-self-supervised-cross-lingual-speech>`_
    * `Emerging Cross-lingual Structure in Pretrained Language Models
      <https://arxiv.org/abs/1911.01464>`_
    * `Word Translation Without Parallel Data
      <https://arxiv.org/abs/1710.04087>`_
    * `Very Deep Convolutional Networks for Text Classification
      <https://arxiv.org/abs/1606.01781>`_
    * `XTREME-S: Evaluating Cross-lingual Speech Representations
      <https://arxiv.org/abs/2203.10752>`_
    * `DeepSpeed Compression: A composable library for extreme compression and zero-cost quantization
      <https://www.microsoft.com/en-us/research/blog/deepspeed-compression-a-composable-library-for-extreme-compression-and-zero-cost-quantization/>`_
    * `Towards Robust Deep Learning using Entropic Losses
      <https://arxiv.org/abs/2208.03566>`_
    * `Few-shot Learning with Retrieval Augmented Language Models
      <https://arxiv.org/abs/2208.03299>`_
    * `Multi-instrument Music Synthesis with Spectrogram Diffusion
      <https://arxiv.org/abs/2206.05408>`_
    
    Machine Learning
    
    * `On the consistency of supervised learning with missing values
      <https://arxiv.org/abs/1902.06931>`_
    * `Why do tree-based models still outperform deep learning on tabular data?
      <https://hal.archives-ouvertes.fr/hal-03723551>`_
    * `Evaluating machine learning models and their diagnostic value
      <https://hal.inria.fr/hal-03682454/>`_
    
    Ecologie
    
    * `Measuring the Carbon Intensity of AI in Cloud Instances
      <https://arxiv.org/abs/2206.05229>`_
    
    Un site
    
    * `paperwithcode <https://paperswithcode.com/>`_
    
    Librairies
    
    * `TorchArrow <https://github.com/pytorch/torcharrow>`_
    
    Un benchmark
    
    * `MIXED PRECISION TRAINING IN PRACTICE
      <https://pytorch.org/blog/what-every-user-should-know-about-mixed-precision-training-in-pytorch/?utm_source=twitter&utm_medium=organic_social&utm_campaign=blog&utm_content=mixed-precision-training-in-pytorch>`_
    
    Autres articles
    
    * `On the Principles of Parsimony and Self-Consistency for the Emergence of Intelligence
      <https://arxiv.org/abs/2207.04630>`_
    * `Shift-Curvature, SGD, and Generalization
      <https://arxiv.org/abs/2108.09507>`_




.. blogpostagg::
    :title: Visualisation de modèles
    :date: 2018-07-12
    :keywords: netron
    :categories: articles
    :rawfile: 2018/2018-07-12_ml.rst

    `Netron <https://github.com/lutzroeder/Netron>`_ : cet outil n'explique pas vraiment
    mais permet de visualiser des modèles de machine learning.
    C'est un pas dans la bonne direction, il semble assez populaire
    sur GitHub. Il est sans doute amené à évoluer
    (référencé dans :ref:`l-interpretabilite-ml`).
    `VisualDL <https://github.com/PaddlePaddle/VisualDL>`_
    est un outil similaire dédié au deep learning.
    

    ...




.. blogpostagg::
    :title: Quelques articles à lire
    :date: 2018-07-03
    :keywords: matrix factorization,category encoder
    :categories: articles
    :rawfile: 2018/2018-07-03_articles.rst

    Lectures d'été.
    

    ...





----

|rss_image|  **articles - 1/1** :ref:`2022-10 (1) <ap-month-2022-10-0>` :ref:`2022-12 (2) <ap-month-2022-12-0>` :ref:`2023-01 (1) <ap-month-2023-01-0>` :ref:`2023-02 (1) <ap-month-2023-02-0>` :ref:`2023-04 (1) <ap-month-2023-04-0>`